Language Models (LMs) often must integrate facts they memorized in
pretraining with new information that appears in a given context. These two
sources can disagree, causing competition within the model, and it is unclear
how an LM will resolve the conflict. On a dataset that queries for knowledge of
world capitals, we investigate both distributional and mechanistic determinants
of LM behavior in such situations. Specifically, we measure the proportion of
the time an LM will use a counterfactual prefix (e.g., "The capital of Poland
is London") to overwrite what it learned in pretraining ("Warsaw"). On Pythia
and GPT2, the training frequency of both the query country ("Poland") and the
in-context city ("London") highly affect the models' likelihood of using the
counterfactual. We then use head attribution to identify individual attention
heads that either promote the memorized answer or the in-context answer in the
logits. By scaling up or down the value vector of these heads, we can control
the likelihood of using the in-context answer on new data. This method can
increase the rate of generating the in-context answer to 88\% of the time
simply by scaling a single head at runtime. Our work contributes to a body of
evidence showing that we can often localize model behaviors to specific
components and provides a proof of concept for how future methods might control
model behavior dynamically at runtime.

利用头部归因方法控制模型行为，将模型表现局部化，并提供了一种概念验证方法，展示如何在运行时动态地控制模型行为。